Abstract: Techniques and systems are described that leverage computer vision as part of search to expand functionality of a computing device available to a user and increase operational computational efficiency as well as efficiency in user interaction. In a first example, user interaction with items of digital content is monitored. Computer vision techniques are used to identify digital images in the digital content, objects within the digital images, and characteristics of those objects. This information is used to assign a user to a user segment of a user population which is then used to control output of subsequent digital content to the user, e.g., recommendations, digital marketing content, and so forth.

Abstract: Gesture functionality is provided in a computing environment. In example embodiments, a gesture input is received. A style difference is identified between a known gesture input of a set of known gesture inputs and the received gesture input. The set of known gesture inputs is caused to be modified to include the style difference by updating a database that stores the set of known gesture inputs.

Abstract: Technology for the improved processing of search queries is provided. In one embodiment, methods may return semantically relevant search results for a search query. During a pre-computing offline processing, an inventory semantic index may be generated and may include inventory binary hashing signatures that are associated with inventory listings, such as goods or services for sell, and the index may be partitioned by categories and shards. When a search query is received, relevant categories are determined using a relevant category recognition service, and a search query binary hashing signature maybe generated for the search query. The relevant categories are searched to determine hamming distances between the inventory binary hashing signatures and the search query binary hashing signature, where the hamming distance indicates semantic relevance.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for automatic image selection for online product catalogs. An image selection system gathers feature data for images of an item included in listings posted to an online marketplace. The image selection system uses the feature data as input in a machine learning model to determine probability scores indicating an estimated probability that each image is suitable to represent the item. The machine learning model is trained based on a set of training images of the item that have been labeled to indicate whether they are suitable to represent the image. The image selection system compares the probability scores and selects an image to represent the item as a stock image based on the comparison.

Abstract: Systems and methods for integrating and managing an authentication and automated return process are provided. In example embodiments, a network system receives, via a first application protocol interface (API) call from an authenticator system, an indication that an item associated with a transaction is not authentic, whereby the transaction occurred on the network system between accounts associated with a first and second client device. Based on the receiving of the indication, the network system automatically causes a return to be created at the network system. The network system then automatically triggers processing of the return including transferring funds to the account associated with the first client device, the account associated with the first client device previously providing payment to purchase the item and the account associated with the second client device providing the item for sale.

Abstract: Understanding emojis in the context of online experiences is described. In at least some embodiments, text input is received and a vector representation of the text input is computed. Based on the vector representation, one or more emojis that correspond to the vector representation of the text input are ascertained and a response is formulated that includes at least one of the one or more emojis. In other embodiments, input from a client machine is received. The input includes at least one emoji. A computed vector representation of the emoji is used to look for vector representations of words or phrases that are close to the computed vector representation of the emoji. At least one of the words or phrases is selected and at least one task is performed using the selected word(s) or phrase(s).

Abstract: The “free world replication protocol” makes use of client computing resources, wherein the clients are not part of the replicated key-value store, but instead reside in the “free world” outside of the dedicated resources of the nodes of the replicated key-value store. In the free world replication protocol, only a single “write” client is authorized to modify the key-value store at any time but any number of clients may be authorized to read data from the key-value store. The write client sends its transactions to multiple nodes in the replicated key-value store. As a result, the latency between the transaction being sent from the client and the transaction being received by the multiple nodes is reduced. A consensus protocol, driven by a master node, is used to periodically ensure consistency, but the data transactions themselves do not make use of a master node.

Abstract: There are provided systems and methods for synchronized media capturing for an interactive scene. A user at a venue may watch an event unfold at the venue. The venue may include wireless beacons established throughout the venue. The wireless beacons may be configured to establish short range wireless communications with the user's device. Once a connection is established, the wireless beacons may instruct the user's device to capture media of an instance during the event. The wireless beacons may similar instruct other user's devices to capture media of the instance at the same time, thereby synchronizing media capturing of a particular instance during the event. The user may review the media and select to delete the media or upload the media to a media sharing service. The server may further process the media into an interactive scene.

Abstract: Systems and methods for authenticating requests to use an Application Programming Interface (“API”) are described. In some embodiments, a request to use an API is received. Based on a comparison of the request to use the API with a pattern of activity associated with the client, a determination is made whether the client deviates from an expected behavior. Once a determination that the client deviates from the expected behavior is made, an authentication challenge is generated and issued. In some embodiments, the comparison of the request to use the API with a pattern of activity involves comparing transactional attributes of the request to use the API with past client behavior.

Abstract: In an example embodiment, a method of identifying an item depicted in an image is provided. In this method, the image depicting the item is accessed; in addition, other images and their item identifiers are also accessed. A match of the image with one of the other images is identified. With a match, the image is then associated with an item identifier of the matched image.

Abstract: A system and method of providing user customizable web advertisements are disclosed. In some embodiments, the system may include a non-transitory, computer-readable medium storing computer-executable instructions and one or more processors. When the one or more processors execute the computer-executable instructions, the processors may be configured to receive a customizable advertisement, the customizable advertisement having at least one customizable portion. When a customizable portion is selected, the one or more processors may display a plurality of customization options for the at least one customizable portion. The one or more processors may be further configured to receive a selection of a customization option from the plurality of customization options. The one or more processors may then apply the selected customization option to the customizable portion of the customizable advertisement.

Abstract: In various example embodiments, a system and method for adjusting a user interface according to a cognitive mode is disclosed. In one example embodiment, a method includes receiving a plurality of user events based on a user interacting with a system, determining a cognitive operating mode of the user based on the user events, with the cognitive operating mode selected from a predefined set of cognitive operating modes, and modifying a user interface element according to the cognitive operating mode of the user.

Abstract: Artificial assistant system notification techniques are described that overcome the challenges of conventional search techniques. In one example, a user profile is generated to describe aspects of products or services learned through natural language conversations between a user and an artificial assistant system. These aspects may include price as well as non-price aspects such as color, texture, material, and so forth. To learn the aspects, the artificial assistant system may leverage spoken utterances and text initiated by the user as well as learn the aspects from digital images output as part of the conversation. Once generated, the user profile is then usable by the artificial assistant system to assist in subsequent searches.

Abstract: A system for assisting users in listing items for sale in an electronic marketplace is disclosed. A video is received from a user device associated with a user, the video including a video stream depicting a plurality of items to be listed for sale in the electronic marketplace. Respective images depicting respective items among the plurality of items are obtained from the video stream, and respective attributes of the respective items among the plurality of items are extracted from the video. Respective listings for sale of the respective items are generated based at least in part on the respective attributes of the respective items among the plurality of items, and the respective listings for sale of the respective items are displayed to the user.

Abstract: Systems and methods for an e-commerce enabled digital whiteboard are described. The system receives first initialization information, over a network, from a mobile device that includes a description of a first vehicle and a description of a first repair for the first vehicle. The first initialization information is stored in a first context. The system further receives a first request to attach the first context to an online collaborative workspace. The system further attaches the first context to an online collaborative marker that is associated with the online collaborative workspace. The system further generates a first interface based on the first context. The first interface includes the online collaborative interactive workspace including a first repair schematic including instructions for the first repair for the first vehicle. The system further receives a second request, over the network, from the mobile device that is also processed based on the first context.

Abstract: A method and a system include receiving an alert enrollment request based on a user selection from a mobile device of a user, the mobile device corresponding to a communication endpoint identifier; generating a user interface element that corresponds to a confirmation of an option to initiating a communication channel; in response to receiving an indication of the confirmation, initiating the communication channel via the mobile device; and transmitting an invitation of a survey communication through the communication channel, the survey communication including an identity verification request associated with a selected phrase to be repeated by the user.

Abstract: Techniques for resource allocation with content creators are described that overcome the challenges of conventional techniques by supporting customized digital content generation and resource allocation specified by content creators of digital content. In one example, a content provider system, based on user input received via a control, specifies the portions of a resource allocation to be shared. A first portion is configured to be shared with a content creator of digital content, the digital content including service access data configured to access a digital service. A second portion is also configured to be shared with a client device that utilizes the service access data to access the digital service. Digital content is generated based on the specified portions and is transmitted. Upon access by the client device to the digital service, an indication of receipt of the first portion of the resource allocation is displayed by the content provider system.

Abstract: Systems and methods disclosed herein may operate to adjust display orientation of a user device based on facial landmark information. In various embodiments, information identifying and describing a facial landmark of a user may be received via a user device corresponding to the user. Head orientation of the user may be determined based at least in part on the information identifying and describing the facial landmark. A display unit of the user device may be automatically signaled to align display orientation of contents being presented with the head orientation as determined based at least in part on the information identifying and describing the facial landmark.

Abstract: Systems and methods for organizing structured items in an e-commerce system are presented. In some aspects, the systems and methods may include a back-end structured item organizing system associated with a front-end category mapping system which is configured to process use case requests. In some aspects, a use case request may identify an item for classification by the back-end structured organizing system. In some aspects, the described systems and methods may select a listing bucket from a set of listing buckets of the back-end structured organizing system based on attribute values indicated in the use case request, and may cause a user interface of the front-end category mapping system to display one or more characteristics associated with items categorized within the selected listing bucket.

Abstract: Systems and methods to provide a prioritized shopping system are discussed. For example, a method can include receiving a list of target items, receiving busyness data for a plurality of local merchants, developing a prioritized shopping plan, and communicating the prioritized shopping plan to a mobile device. Each target item in the list of target items can represents a product or service that a user has indicated an interest in purchasing. The prioritized shopping plan is based at least in part on the busyness data and the list of target items. Busyness data provides an indication of traffic levels within at least a portion of the plurality of local merchants.

Abstract: Methods and systems for automatic publication of listings on an ecommerce system are disclosed. In one aspects, a method include filtering historical item listings for items to those items having a similarity to a particular item, determining predictions of future sales prices over future time periods for the particular item based on the filtered historical items, the determined predictions including future sales prices having different probabilities of sale completion, receiving a user selection indicating one or more predictions of future sales prices over one or more future time periods; and determining a time to initiate publication of an on online listing for the particular item based on the selected one or more predictions.

Abstract: Disclosed are methods and systems for displaying an indication of a number of items in a user interface. Some aspects include processing circuitry and hardware memory storing instructions that when executed cause the processing circuitry to perform operations. The operations may include receiving input defining an item, receiving sensor data for the item, and displaying a number of items in the environment based on the sensor data.

Abstract: A computer implemented method to present digital images may include storing a digital image in a database and applying a digital image processing technique to the digital image to identify a region of interest of the digital image. The method may also include storing region data that identifies the region of interest of the digital image in the database and receiving a request for information associated with the digital image from a digital device. In response to the request, the method may include providing the digital image and the region data for transmission to the digital device, the digital device configured to adjust a cropping view of the digital image based on the region data to display the region of interest of the digital image.

Abstract: Methods, systems, and apparatus for conducting a video conference. A location of one or more sets of eyes in an image may be determined. The relative location of an image capture device and/or a portion of a display device may be adjusted based on the determined location.

Abstract: An apparatus and method to adjust item recommendations are disclosed herein. A first image attribute of a query image is compared to a second image attribute of each of a plurality of inventory images of a plurality of inventory items to identify the inventory items similar to the query image. Item recommendations comprising the identified inventory items in a first listing order are provided for display at a remote device. A second listing order of the identified inventory items is determined based on a user preference for a particular one of the identified inventory items. At least the second listing order is provided to the remote device for re-display of the item recommendations in accordance with the second listing order.

Abstract: Technologies are shown for storing sub-component state data for a resource on a blockchain involving generating a resource data block that corresponds to a resource that includes links that correspond to sub-components of the resource, generating a first sub-component state data block for a sub-component of the resource on a blockchain that includes first state data for the first sub-component, and setting the link for the sub-component to reference the first sub-component state data block. Subsequently, a second sub-component state data block can be generated for the sub-component with second state data and the second sub-component state data block linked to the first sub-component state data block.

Abstract: Systems and methods for managing keys in a computer memory are described. In some embodiments, location addresses are determined for two key elements. A periodic time interval that is based on a time duration for performing a transaction involving a distance between the key elements is determined. One key element may be stored at a location address and then relocated to another location address after the periodic time interval has passed. In some embodiments, areas the computer memory may remain static during relocation of the key element.

Abstract: In accordance with one or more embodiments of the present disclosure, systems and methods for publishing and/or sharing media presentations over a network comprise communicating with a user and one or more distribution channels via the network, gathering media resources based on user input, creating a media presentation with the media resources based on user input, and publishing the media presentation by distributing the media presentation to the one or more distribution channels via the network. In one aspect, publishing comprises directly emailing the media presentation to one or more other users via the network. In another aspect, publishing comprises providing a link to one or more other users via the network for direct access to the media presentation. In still another aspect, publishing comprises obtaining and embedding source code for the media presentation in a web page associated with one or more of the distribution channels via the network.

Abstract: Example embodiments provide a system that uses a conversational agent to collect information and publish the information on a network. A computer-implemented conversational agent establishes a communication session with a user and receives conversational information via a simulated conversation between the user and the computer-implemented conversational agent via the communication session, whereby the conversational information comprises information to be published. The computer-implemented conversational agent also receives, via a graphical user interface, an upload of an image that is associated with the information to be published. The computer-implemented conversational agent then causes publication of the information to be published and the uploaded image.

Abstract: Visual diagram searching techniques are described herein. A visual diagram service enables users to efficiently search for data for item parts even in cases where the name of the item part is unknown. In one or more examples, search query input to locate item parts of an item is received via a user interface displayed by at least one computing device. A visual diagram of the item is displayed in the user interface. The visual diagram includes selectable portions mapped to respective item parts depicted in the corresponding selectable portion of the visual diagram. A user selection of one of the selectable portions of the visual diagram of the item is received via the user interface. In response to the user selection, search result data corresponding to the respective item part depicted in the selected selectable portion of the visual diagram of the item is displayed.

Abstract: Automatic workflow generation is described. One or more files containing code statements for accessing and modifying information in a destination database is received. The code statements are parsed from the one or more files and dependencies between the code statements are determined. A dependency graph is built by arranging the code statements according to the dependencies between the code statements. The dependency graph is partitioned by identifying at least one barrier code statement having an unclear dependency and dividing the dependency graph between code statements occurring prior to the at least one barrier code statement and code statements occurring after the at least one barrier code statement. Jobs are scheduled based on the partitioned dependency graph, and the code statements are annotated according to the scheduled jobs. A workflow is then automatically generated based on the annotated code statements.

Abstract: A computer-implemented system and method for pool-based identity authentication for service access without use of stored credentials is disclosed. The method in an example embodiment includes providing provisioning information for storage in a provisioning repository; receiving a service request from a service consumer, the service request including requestor identifying information; generating an authentication request to send to an authentication authority, the authentication request including requestor identifying information; receiving validation of an authenticated service request from the authentication authority; and providing the requested service to the service consumer.

Abstract: A method and system for analyzing sites is described. A scanner module scans listings of an online publication. A quality engine analyzes the quality of the listings. A data collection module collects defective conditions of the listings determined by the quality engine. A report module reports the defective conditions of the listings. An auto correction module automatically corrects at least a first portion of the defective conditions of the listings. A manual correction module enables an operator of the online publication to correct at least a second portion of the defective conditions of the listings.

Abstract: Technologies are shown for selecting a provider to service a client service request using a predictive metrics based consensus protocol to select a provider and create a service request transaction block to service the client service request. A client service request is received and forwarded to a set of providers. Proposed transactions are received from the providers and scored based on a predictive metric. A proposal transaction is selected based on the scoring and the selected transaction is written as a block on a service transaction blockchain. The provider for the selected transaction detects the block on the blockchain and performs the requested service. The client detects the block on the blockchain and transfers payment to the provider. Selection can be based on predictive metrics in the providers or macro metrics determined in miner nodes in combination with provider reputation, currency, load sharing, fairness, provisioning, and static and dynamic criteria.

Abstract: Systems and methods are provided for automatically generating a video associated with an item in the marketplace. An image receiver receives images associated with an item of an item listing. An image extractor generates visual descriptors for each image through computer vision analysis and extracts a unique set of images by removing redundant images. An image sorter sorts images in the unique set of images based on an item category and generates a sequence of images for generating a video. A text placer automatically identifies a region in an image and inserts text into the image using textual attributes as predicted by a model. A video data optimizes a generated video using another model trained based on manual adjustments previously made to other exemplary video data. The disclosed technology publishes the automatically generated video data for viewing by viewers in the marketplace.

Abstract: Systems and methods are provided for automatically generating a thumbnail for a video on an online shopping site. The disclosed technology automatically generates a thumbnail for a video, where the thumbnail represents an item but not necessarily content of the video. A thumbnail generator receives a video that describes the item and an ordered list of item images associated with the item used in an item listing. The thumbnail generator extracts video frames from the video based on sampling rules and determines similarity scores for the sampled video frames. A similarity score indicates a degree of similarity between content of a video frame and an item image. The thumbnail generator determines weighted similarity scores based item images and occurrences of sampled video frames in the video. The disclosed technology generates a thumbnail for the video by selecting a sample video frame based on the weighted similarity scores.

Abstract: Techniques for lip-reading session triggering events are described. A computing device is equipped with lip-reading capability that enables the device to “read the lips” (i.e., facial features) of a user. The computing device determines when a triggering event occurs to automatically cause the computing device to switch from one input type to a lip-reading session. Lip-reading is also used in conjunction with other types of inputs to improve accuracy of the input. Machine learning is used to personalize the lip-reading capability of the computing device for a particular user.

Abstract: A method of setting a listing price for an item is disclosed. One or attributes of the item are determined based on data entered into fields of a listing user interface. One or more additional items are identified based on a comparison of one or more attributes of the one or more additional items with the one or more attributes of the item. Sales information associated with the one or more additional items is determined. A range of suggested prices and at least some of the sales information is incorporated into a selection user interface region of the listing user interface. Based on a selection of a suggested price from the range of suggested prices, a preview of the listing as it would appear in a search results page with the one or more additional items is presented in the listing user interface.

Abstract: Systems and methods are provided for identifying a first user account based on an indication of purchase of a first item; identifying a second user account associated with the first user account; determining a shared characteristic between the first item of the first user account and a second item in an online container associated with the second user account; determining a user interest of the second item based on user attribute data associated with the second user account and the shared characteristic; removing the second item from the online container based on the determining of the user interest; and causing display of a notification on a user interface of a device associated with the second user account, the notification including an indication of the second item being removed from the online container based on the indication of purchase of the first item.

Abstract: A method of event monitoring includes identifying a monitored event that produces a physical phenomenon that is observable and identifiable. The method includes identifying a particular input that is representative of the physical phenomenon and that suggests an occurrence of the monitored event. The method includes communicating, from the first computing device, to a second computing device that includes a sensor at least a portion of the particular input that is used for recognition of the monitored event in an environment of the second computing device by the sensor. The method includes receiving, at the first computing device from the second computing device, an event message that indicates the particular input is observed by the sensor. In response to reception of the event message, the method includes generating an alarm message that indicates the occurrence of the monitored event is observed in the environment of the second computing device.

Abstract: Techniques for modifying a garment based on gestures are presented herein. An access module can access a first set of sensor data from a first sensor, and a second set of sensor data from a second sensor. A garment simulation module can generate a three-dimensional (3D) garment model of a garment available for sale draped on an avatar based on the first set of sensor data and the second set of sensor data. A display module can cause a presentation, on a display of a device, of the 3D garment model draped on the avatar. Additionally, the garment simulation module can determine a modification gesture associated with the 3D garment model draped on the avatar based on the first set of sensor data and the second set of sensor data. Furthermore, the garment simulation module can modify the 3D garment model based on the determined modification gesture.

Abstract: A system and method for using super geo-fences to improve efficiency of geo-fences is disclosed. A system determines a geo-fence density based on a number of geo-fences in an area around a client system. In response to determining the geo-fence density is greater than a predetermined density value, the system selects a number of geo-fences that is greater than a fixed number of geo-fences that the client system is capable of handling. The system groups the selected geo-fences into a first and second group of geo-fences and generates a super geo-fence that encompasses the first group. The system transmits the first and second group of geo-fences and the super geo-fence to an application stored at the client device. The application adds geo-fence data corresponding to the second group to the client system in response to detecting the client system crossing a boundary of the super geo-fence.

Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.

Abstract: Camera platform techniques are described. In an implementation, a plurality of digital images and data describing times, at which, the plurality of digital images are captured is received by a computing device. Objects of clothing are recognized from the digital images by the computing device using object recognition as part of machine learning. A user schedule is also received by the computing device that describes user appointments and times, at which, the appointments are scheduled. A user profile is generated by the computing device by training a model using machine learning based on the recognized objects of clothing, times at which corresponding digital images are captured, and the user schedule. From the user profile, a recommendation is generated by processing a subsequent user schedule using the model as part of machine learning by the computing device.

Abstract: Systems and methods for managing a multi-listing combined offer are provided. A networked system receives an indication to add a combination of items from multiple sellers into a virtual cart. In response, the networked system causes presentation of a user interface showing a combination of items from multiple sellers. The networked system receives, from the buyer, a buyer offer price for the combination of items. In response, the networked system accesses, from a data storage, item information for each item of the combination of items, whereby the item information includes a seller identifier, an original item price, and shipping cost for each item. The networked system then generates, based on the accessed item information and the buyer offer price, a split offer price for each seller, whereby the split offer price is a split of the buyer offer price. The split offer price is then presented to each corresponding seller.

Abstract: Generally discussed herein are systems, apparatuses, and methods for providing information regarding a product that is unique to a geographical region. In one or more embodiments a method may include determining a location of a user, receiving information indicative of one or more products unique to a particular geographical region corresponding to the determined location of the user, wherein each of the one or more products are offered for sale in the particular region by one or more merchants, and providing information about at least one of the products and about a merchant, from the one or more merchants, offering that product for sale in the geographical region.

Abstract: Example embodiments provide a multi-currency cart and checkout. In example embodiments, a currency accepted and a payment option for each item in a multi-currency cart is identified. A plurality of currency groups is generated based on the currency and payment options, whereby each currency group comprises one or more items having a same payment option and accepting a same currency. A multi-currency checkout user interface (UI) is presented on a client device that presents the plurality of currency groups and a pay selector for each of the plurality of the currency groups. An updated multi-currency checkout UI is presented in response to processing payment for a selected one of the plurality of currency groups. The updated multi-currency UI comprises a confirmation for payment for the selected one of the plurality of currency groups and remaining currency groups of the plurality of currency groups.

Abstract: In various example embodiments, a system and method for data mesh-based environmental augmentation are presented. Attribute data associated with a user may be received from a plurality of attribute sources. A portion of the attribute data may include real-time data. A portion of the real-time data indicative of an identity of the user may be identified. The identity of the user may be authenticated with respect to the real-time data by analyzing the identified portion of the real-time data. Based on the authentication of the identity of the user, a user activity being performed by the user may be identified based on the real-time data, and the user activity may be augmented according to a user setting.

Abstract: A machine may be configured to execute a machine-learning process for identifying and understanding fine properties of various items of various types by using images and associated corresponding annotations, such as titles, captions, tags, keywords, or other textual information applied to these images. By use of a machine-learning process, the machine may perform property identification accurately and without human intervention. These item properties may be used as annotations for other images that have similar features. Accordingly, the machine may answer user-submitted questions, such as “What do rustic items look like?,” and items or images depicting items that are deemed to be rustic can be readily identified, classified, ranked, or any suitable combination thereof.

Abstract: Camera platform techniques are described. In an implementation, a plurality of digital images and data describing times, at which, the plurality of digital images are captured is received by a computing device. Objects of clothing are recognized from the digital images by the computing device using object recognition as part of machine learning. A user schedule is also received by the computing device that describes user appointments and times, at which, the appointments are scheduled. A user profile is generated by the computing device by training a model using machine learning based on the recognized objects of clothing, times at which corresponding digital images are captured, and the user schedule. From the user profile, a recommendation is generated by processing a subsequent user schedule using the model as part of machine learning by the computing device.